Estimation of Head Motion in Structural MRI and its Impact on Cortical Thickness Measurements in Retrospective Data

TL;DR

This paper introduces a deep learning method to estimate head motion in retrospective MRI scans, enabling correction of motion-induced biases in cortical thickness measurements without specialized hardware.

Contribution

We develop a 3D CNN that accurately estimates motion from routine MRI scans, generalizing across datasets and improving neuroanatomical analysis reliability.

Findings

Achieved R^2=0.65 with manual labels for motion estimation.

Detected significant cortical thickness-motion correlations in most datasets.

Correlated predicted motion with subject age, consistent with prior research.

Abstract

Motion-related artifacts are inevitable in Magnetic Resonance Imaging (MRI) and can bias automated neuroanatomical metrics such as cortical thickness. These biases can interfere with statistical analysis which is a major concern as motion has been shown to be more prominent in certain populations such as children or individuals with ADHD. Manual review cannot objectively quantify motion in anatomical scans, and existing quantitative automated approaches often require specialized hardware or custom acquisition protocols. Here, we train a 3D convolutional neural network to estimate a summary motion metric in retrospective routine research scans by leveraging a large training dataset of synthetically motion-corrupted volumes. We validate our method with one held-out site from our training cohort and with 14 fully independent datasets, including one with manual ratings, achieving a representative $R^2 = 0.65$ versus manual labels and significant thickness-motion correlations in 12/15 datasets. Furthermore, our predicted motion correlates with subject age in line with prior studies. Our approach generalizes across scanner brands and protocols, enabling objective, scalable motion assessment in structural MRI studies without prospective motion correction. By providing reliable motion estimates, our method offers researchers a tool to assess and account for potential biases in cortical thickness analyses.